© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 18303
    Prev
    Next
    INDEX
    Explanations

    . or sentence end

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dings
    -0.11
     garg
    -0.11
    atables
    -0.11
     irm
    -0.10
    akin
    -0.10
    Ah
    -0.10
    ATOR
    -0.10
     Eight
    -0.10
     Held
    -0.10
     Wanna
    -0.10
    POSITIVE LOGITS
    alis
    0.08
    asso
    0.08
    icht
    0.08
    éc
    0.07
    apper
    0.07
     ensuing
    0.07
    ande
    0.07
    pras
    0.07
    ER
    0.07
    iced
    0.06
    Activations Density 0.002%

    No Known Activations